| { |
| "best_metric": 0.9109156238384339, |
| "best_model_checkpoint": "./my_unified_model_classification/checkpoint-1446", |
| "epoch": 1.7962732919254658, |
| "eval_steps": 241, |
| "global_step": 1446, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.062111801242236024, |
| "grad_norm": 63.5, |
| "learning_rate": 3.125e-06, |
| "loss": 1.0657, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.12422360248447205, |
| "grad_norm": 76.0, |
| "learning_rate": 6.25e-06, |
| "loss": 0.7557, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.18633540372670807, |
| "grad_norm": 78.5, |
| "learning_rate": 9.375000000000001e-06, |
| "loss": 0.6955, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.2484472049689441, |
| "grad_norm": 67.5, |
| "learning_rate": 9.724137931034484e-06, |
| "loss": 0.6802, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.2993788819875776, |
| "eval_accuracy": 0.6955305091333074, |
| "eval_auc": 0.7418841739149382, |
| "eval_f1": 0.7681013557515837, |
| "eval_false_negatives": 1514, |
| "eval_false_positives": 2403, |
| "eval_loss": 0.5827530026435852, |
| "eval_precision": 0.7296962879640045, |
| "eval_recall": 0.8107736532933383, |
| "eval_runtime": 455.1837, |
| "eval_samples_per_second": 28.263, |
| "eval_specificity": 0.5059621710526315, |
| "eval_steps_per_second": 0.222, |
| "eval_true_negatives": 2461, |
| "eval_true_positives": 6487, |
| "step": 241 |
| }, |
| { |
| "epoch": 0.2993788819875776, |
| "step": 241, |
| "train_accuracy": 0.687, |
| "train_auc": 0.7550223214285714, |
| "train_f1": 0.7619771863117871, |
| "train_false_negatives": 107, |
| "train_false_positives": 206, |
| "train_loss": 0.5734015107154846, |
| "train_precision": 0.7086280056577087, |
| "train_recall": 0.8240131578947368, |
| "train_runtime": 35.3914, |
| "train_samples_per_second": 28.255, |
| "train_specificity": 0.4744897959183674, |
| "train_steps_per_second": 0.226, |
| "train_true_negatives": 186, |
| "train_true_positives": 501 |
| }, |
| { |
| "epoch": 0.3105590062111801, |
| "grad_norm": 18.25, |
| "learning_rate": 9.379310344827586e-06, |
| "loss": 0.6068, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.37267080745341613, |
| "grad_norm": 12.8125, |
| "learning_rate": 9.03448275862069e-06, |
| "loss": 0.6149, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.43478260869565216, |
| "grad_norm": 32.5, |
| "learning_rate": 8.689655172413793e-06, |
| "loss": 0.5789, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.4968944099378882, |
| "grad_norm": 24.125, |
| "learning_rate": 8.344827586206897e-06, |
| "loss": 0.5587, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.5590062111801242, |
| "grad_norm": 32.5, |
| "learning_rate": 8.000000000000001e-06, |
| "loss": 0.5215, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.5987577639751552, |
| "eval_accuracy": 0.7639331519626895, |
| "eval_auc": 0.8317355812636907, |
| "eval_f1": 0.8263479901652467, |
| "eval_false_negatives": 775, |
| "eval_false_positives": 2262, |
| "eval_loss": 0.5106464624404907, |
| "eval_precision": 0.761593591905565, |
| "eval_recall": 0.9031371078615174, |
| "eval_runtime": 454.6656, |
| "eval_samples_per_second": 28.296, |
| "eval_specificity": 0.5349506578947368, |
| "eval_steps_per_second": 0.222, |
| "eval_true_negatives": 2602, |
| "eval_true_positives": 7226, |
| "step": 482 |
| }, |
| { |
| "epoch": 0.5987577639751552, |
| "step": 482, |
| "train_accuracy": 0.806, |
| "train_auc": 0.8575379640105948, |
| "train_f1": 0.8596237337192475, |
| "train_false_negatives": 45, |
| "train_false_positives": 149, |
| "train_loss": 0.46753111481666565, |
| "train_precision": 0.7994616419919246, |
| "train_recall": 0.9295774647887324, |
| "train_runtime": 35.3613, |
| "train_samples_per_second": 28.279, |
| "train_specificity": 0.5872576177285319, |
| "train_steps_per_second": 0.226, |
| "train_true_negatives": 212, |
| "train_true_positives": 594 |
| }, |
| { |
| "epoch": 0.6211180124223602, |
| "grad_norm": 30.0, |
| "learning_rate": 7.655172413793104e-06, |
| "loss": 0.5005, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.6832298136645962, |
| "grad_norm": 41.25, |
| "learning_rate": 7.310344827586208e-06, |
| "loss": 0.4762, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.7453416149068323, |
| "grad_norm": 44.75, |
| "learning_rate": 6.9655172413793105e-06, |
| "loss": 0.4371, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.8074534161490683, |
| "grad_norm": 22.75, |
| "learning_rate": 6.620689655172415e-06, |
| "loss": 0.4143, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.8695652173913043, |
| "grad_norm": 30.0, |
| "learning_rate": 6.275862068965518e-06, |
| "loss": 0.3773, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.8981366459627329, |
| "eval_accuracy": 0.8326467158958414, |
| "eval_auc": 0.9111949385233095, |
| "eval_f1": 0.8749637028863465, |
| "eval_false_negatives": 468, |
| "eval_false_positives": 1685, |
| "eval_loss": 0.39668816328048706, |
| "eval_precision": 0.8172054675634628, |
| "eval_recall": 0.9415073115860517, |
| "eval_runtime": 454.4318, |
| "eval_samples_per_second": 28.31, |
| "eval_specificity": 0.653577302631579, |
| "eval_steps_per_second": 0.222, |
| "eval_true_negatives": 3179, |
| "eval_true_positives": 7533, |
| "step": 723 |
| }, |
| { |
| "epoch": 0.8981366459627329, |
| "step": 723, |
| "train_accuracy": 0.867, |
| "train_auc": 0.9420544944951664, |
| "train_f1": 0.8976135488837568, |
| "train_false_negatives": 25, |
| "train_false_positives": 108, |
| "train_loss": 0.3339703679084778, |
| "train_precision": 0.8437047756874095, |
| "train_recall": 0.9588815789473685, |
| "train_runtime": 35.394, |
| "train_samples_per_second": 28.253, |
| "train_specificity": 0.7244897959183674, |
| "train_steps_per_second": 0.226, |
| "train_true_negatives": 284, |
| "train_true_positives": 583 |
| }, |
| { |
| "epoch": 0.9316770186335404, |
| "grad_norm": 20.375, |
| "learning_rate": 5.9310344827586205e-06, |
| "loss": 0.3688, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.9937888198757764, |
| "grad_norm": 37.0, |
| "learning_rate": 5.586206896551725e-06, |
| "loss": 0.358, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.0559006211180124, |
| "grad_norm": 22.125, |
| "learning_rate": 5.241379310344829e-06, |
| "loss": 0.2656, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.1180124223602483, |
| "grad_norm": 20.875, |
| "learning_rate": 4.896551724137931e-06, |
| "loss": 0.2446, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.1801242236024845, |
| "grad_norm": 33.25, |
| "learning_rate": 4.551724137931035e-06, |
| "loss": 0.26, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.1975155279503105, |
| "eval_accuracy": 0.86677030703459, |
| "eval_auc": 0.9362233426619369, |
| "eval_f1": 0.8912022343531801, |
| "eval_false_negatives": 981, |
| "eval_false_positives": 733, |
| "eval_loss": 0.3193606734275818, |
| "eval_precision": 0.9054559525345027, |
| "eval_recall": 0.8773903262092239, |
| "eval_runtime": 456.2145, |
| "eval_samples_per_second": 28.199, |
| "eval_specificity": 0.8493009868421053, |
| "eval_steps_per_second": 0.221, |
| "eval_true_negatives": 4131, |
| "eval_true_positives": 7020, |
| "step": 964 |
| }, |
| { |
| "epoch": 1.1975155279503105, |
| "step": 964, |
| "train_accuracy": 0.898, |
| "train_auc": 0.9668180434447182, |
| "train_f1": 0.9144295302013423, |
| "train_false_negatives": 56, |
| "train_false_positives": 46, |
| "train_loss": 0.2293623387813568, |
| "train_precision": 0.922165820642978, |
| "train_recall": 0.9068219633943427, |
| "train_runtime": 35.3688, |
| "train_samples_per_second": 28.273, |
| "train_specificity": 0.8847117794486216, |
| "train_steps_per_second": 0.226, |
| "train_true_negatives": 353, |
| "train_true_positives": 545 |
| }, |
| { |
| "epoch": 1.2422360248447206, |
| "grad_norm": 32.25, |
| "learning_rate": 4.206896551724138e-06, |
| "loss": 0.2474, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.3043478260869565, |
| "grad_norm": 29.25, |
| "learning_rate": 3.862068965517241e-06, |
| "loss": 0.23, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.3664596273291925, |
| "grad_norm": 17.375, |
| "learning_rate": 3.517241379310345e-06, |
| "loss": 0.2236, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.4285714285714286, |
| "grad_norm": 22.25, |
| "learning_rate": 3.172413793103449e-06, |
| "loss": 0.2283, |
| "step": 1150 |
| }, |
| { |
| "epoch": 1.4906832298136645, |
| "grad_norm": 28.25, |
| "learning_rate": 2.827586206896552e-06, |
| "loss": 0.2255, |
| "step": 1200 |
| }, |
| { |
| "epoch": 1.4968944099378882, |
| "eval_accuracy": 0.8846482705013603, |
| "eval_auc": 0.9448943522273533, |
| "eval_f1": 0.9082704907899617, |
| "eval_false_negatives": 654, |
| "eval_false_positives": 830, |
| "eval_loss": 0.28922486305236816, |
| "eval_precision": 0.8984957808487221, |
| "eval_recall": 0.9182602174728159, |
| "eval_runtime": 456.3143, |
| "eval_samples_per_second": 28.193, |
| "eval_specificity": 0.829358552631579, |
| "eval_steps_per_second": 0.221, |
| "eval_true_negatives": 4034, |
| "eval_true_positives": 7347, |
| "step": 1205 |
| }, |
| { |
| "epoch": 1.4968944099378882, |
| "step": 1205, |
| "train_accuracy": 0.936, |
| "train_auc": 0.9826765377795963, |
| "train_f1": 0.9488, |
| "train_false_negatives": 31, |
| "train_false_positives": 33, |
| "train_loss": 0.1695481836795807, |
| "train_precision": 0.9472843450479234, |
| "train_recall": 0.9503205128205128, |
| "train_runtime": 35.5418, |
| "train_samples_per_second": 28.136, |
| "train_specificity": 0.9122340425531915, |
| "train_steps_per_second": 0.225, |
| "train_true_negatives": 343, |
| "train_true_positives": 593 |
| }, |
| { |
| "epoch": 1.5527950310559007, |
| "grad_norm": 48.0, |
| "learning_rate": 2.4827586206896555e-06, |
| "loss": 0.2208, |
| "step": 1250 |
| }, |
| { |
| "epoch": 1.6149068322981366, |
| "grad_norm": 27.25, |
| "learning_rate": 2.137931034482759e-06, |
| "loss": 0.2233, |
| "step": 1300 |
| }, |
| { |
| "epoch": 1.6770186335403725, |
| "grad_norm": 26.375, |
| "learning_rate": 1.7931034482758622e-06, |
| "loss": 0.2143, |
| "step": 1350 |
| }, |
| { |
| "epoch": 1.7391304347826086, |
| "grad_norm": 26.875, |
| "learning_rate": 1.4482758620689657e-06, |
| "loss": 0.2227, |
| "step": 1400 |
| }, |
| { |
| "epoch": 1.7962732919254658, |
| "eval_accuracy": 0.8882238631947144, |
| "eval_auc": 0.9479095617776396, |
| "eval_f1": 0.9109156238384339, |
| "eval_false_negatives": 649, |
| "eval_false_positives": 789, |
| "eval_loss": 0.2820975184440613, |
| "eval_precision": 0.9030831593170372, |
| "eval_recall": 0.9188851393575803, |
| "eval_runtime": 455.3256, |
| "eval_samples_per_second": 28.255, |
| "eval_specificity": 0.8377878289473685, |
| "eval_steps_per_second": 0.222, |
| "eval_true_negatives": 4075, |
| "eval_true_positives": 7352, |
| "step": 1446 |
| }, |
| { |
| "epoch": 1.7962732919254658, |
| "step": 1446, |
| "train_accuracy": 0.92, |
| "train_auc": 0.9698240627790284, |
| "train_f1": 0.9361022364217252, |
| "train_false_negatives": 21, |
| "train_false_positives": 59, |
| "train_loss": 0.2072494477033615, |
| "train_precision": 0.9085271317829458, |
| "train_recall": 0.9654036243822076, |
| "train_runtime": 35.3935, |
| "train_samples_per_second": 28.254, |
| "train_specificity": 0.8498727735368957, |
| "train_steps_per_second": 0.226, |
| "train_true_negatives": 334, |
| "train_true_positives": 586 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1610, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 241, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.928340740249223e+18, |
| "train_batch_size": 128, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
